PyTorch implementations of Top-N recommendation, collaborative filtering recommenders.

Last update: Dec 22, 2022

Overview

Recommender System in PyTorch

Implementations of various top-N recommender systems in PyTorch for practice.

Movielens 100k & 1M are used as datasets.

Available models

Model	Paper
BPRMF	Steffen Rendle et al., BPR: Bayesian Personalized Ranking from Implicit Feedback. UAI 2009. Link
ItemKNN	Jun Wang et al., Unifying user-based and item-based collaborative filtering approaches by similarity fusion. SIGIR 2006. Link
PureSVD	Paolo Cremonesi et al., Performance of Recommender Algorithms on Top-N Recommendation Tasks. RecSys 2010. Link
SLIM	Xia Ning et al., SLIM: Sparse Linear Methods for Top-N Recommender Systems. ICDM 2011. Link
P3a	Colin Cooper et al., Random Walks in Recommender Systems: Exact Computation and Simulations. WWW 2014. Link
RP3b	Bibek Paudel et al., Updatable, accurate, diverse, and scalablerecommendations for interactive applications. TiiS 2017. Link
DAE, CDAE	Yao Wu et al., Collaborative denoising auto-encoders for top-n recommender systems. WSDM 2016.Link
MultVAE	Dawen Liang et al., Variational Autoencoders for Collaborative Filtering. WWW 2018. Link
EASE	Harald Steck, Embarrassingly Shallow Autoencoders for Sparse Data. WWW 2019. Link
NGCF	Xiang Wang, et al., Neural Graph Collaborative Filtering. SIGIR 2019. Link
LightGCN	Xiangnan He, et al., LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. SIGIR 2020. Link

Enable C++ evaluation

To evaluate with C++ backend, you have to compile C++ and cython with the following script:

python setup.py build_ext --inplace

If compiled NOT successfully, "evaluation with python backend.." will be printed in the beginning.

How to run

Edit experiment configurations in config.py
Edit model hyperparameters you choose in conf/[MODEL_NAME]
run main.py

Implement your own model

You can add your own model into the framework if:

Your model inherits BaseModel class in models/BaseModel.py
Implement necessary methods and add additional methods if you want.
Make YourModel.conf file in conf
Add your model in models.__init__

Reference

Some model implementations and util functions refers to these nice repositories.

NeuRec: An open source neural recommender library. Repository
RecSys 2019 - DeepLearning RS Evaluation. Paper Repository

PyTorch implementations of Top-N recommendation, collaborative filtering recommenders.

Related tags

Overview

Recommender System in PyTorch

Available models

Enable C++ evaluation

How to run

Implement your own model

Reference

Owner

Yoonki Jeong

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

Python library for loading and using triangular meshes.

A dead simple python wrapper for darknet that works with OpenCV 4.1, CUDA 10.1

Pytorch implementation of SenFormer: Efficient Self-Ensemble Framework for Semantic Segmentation

A Kaggle competition: discriminate gender based on handwriting

Calculates JMA (Japan Meteorological Agency) seismic intensity (shindo) scale from acceleration data recorded in NumPy array

这是一个deeplabv3-plus-pytorch的源码，可以用于训练自己的模型。

Cupytorch - A small framework mimics PyTorch using CuPy or NumPy

Program your own vulkan.gpuinfo.org query in Python. Used to determine baseline hardware for WebGPU.

Repo for paper "Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information"

Robustness between the worst and average case

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

Learning to See by Looking at Noise

Simulation of Self Driving Car

Image classification for projects and researches

A library for researching neural networks compression and acceleration methods.

tf2-keras implement yolov5

A baseline code for VSPW

A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks)

DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion